Battery state monitoring method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a battery state monitoring method and device, electronic equipment and storage medium, and relate to the technical field of batteries. The method comprises: obtaining running data of a target battery; obtaining a first index value corresponding to a first monitoring index according to the time running data, and obtaining a second index value corresponding to a second monitoring index according to the time period running data; obtaining a first parameter of the target battery according to the first index value and a first detection rule, and obtaining a second parameter according to the second index value, a first parameter time period sequence and a second detection rule; and determining state information of the target battery according to the first parameter and / or the second parameter. The battery state monitoring method provided by the embodiments of the present application can monitor the state of the target battery from two dimensions of time and time period, obtain state information that can accurately reflect the running state of the battery, and provide support for the management and maintenance of the battery.

Description

Technical Field

[0001] This application relates to the field of battery technology, and more specifically, to a battery state monitoring method, apparatus, electronic device, and storage medium. Background Technology

[0002] Against the backdrop of continuous scientific and technological development and the energy crisis, the new energy industry has developed rapidly. With the proposal of carbon neutrality and carbon peaking goals, the development of new energy vehicles is progressing at an unprecedented pace. As a core component of new energy vehicles, the power battery industry has also experienced rapid growth in recent years, benefiting from the positive environment of the new energy sector. However, behind this high growth in power battery production, safety issues are increasingly attracting public attention.

[0003] Existing technologies improve battery safety by modifying battery materials and mechanical design, starting from the battery's inherent design. However, after batteries are put into use, safety incidents can still occur due to factors such as the working environment and battery malfunctions. Currently, there is no method to monitor battery safety.

[0004] In this situation, there is an urgent need to provide a battery status monitoring solution to monitor the battery status. Summary of the Invention

[0005] The purpose of this application is to at least solve one of the aforementioned technical defects. The technical solution provided by the embodiments of this application is as follows:

[0006] In a first aspect, embodiments of this application provide a battery state monitoring method, including:

[0007] Acquire the operational data of the target battery; wherein, the operational data includes: time period operational data and current time period operational data; the time period operational data includes time period operational data within the range from the first time period to the second time period; the first time period is earlier than the second time period; the second time period is earlier than or equal to the current time period;

[0008] Based on the time-based operation data, the first indicator value corresponding to the first monitoring indicator is obtained, and based on the time-period operation data, the second indicator value corresponding to the second monitoring indicator is obtained.

[0009] The first parameter of the target battery is obtained based on the first index value and the first detection rule, and the second parameter is obtained based on the second index value, the time period sequence of the first parameter, and the second detection rule; wherein, the first detection rule includes the mapping relationship between the first parameter and the threshold range of the first index value; the time period sequence of the first parameter includes the sequence of the first parameter corresponding to each time point from the first time point to the second time point;

[0010] The state information of the target battery is determined based on the first parameter and / or the second parameter.

[0011] In one optional embodiment of this application, it further includes:

[0012] Determine whether the status information meets the warning conditions;

[0013] If the conditions for issuing an early warning are met, then early warning measures will be taken.

[0014] In one optional embodiment of this application, the first parameter of the target battery is obtained according to the first index value and the first detection rule, specifically including:

[0015] Based on the first indicator value and the first detection rule, determine the target fault type of the target battery and the target warning level corresponding to the target fault type;

[0016] The first parameter is obtained based on the target fault type and the target warning level.

[0017] In one optional embodiment of this application, the second parameter is obtained based on the second indicator value, the first parameter time period sequence, and the second detection rule, specifically including:

[0018] Based on the second index value, the first state of charge (SOC) difference and the second SOC difference, the temperature rise rate and the voltage drop rate are obtained; wherein, the target battery includes at least one battery module; the first SOC difference is the absolute value of the difference between the average SOC value and the minimum SOC value of each battery module; the second SOC difference is the absolute value of the difference between the SOC correction value of each battery module and the average SOC value.

[0019] Based on the time period sequence of the first parameter, the warning frequency of heat-related fault types is obtained;

[0020] The second parameter is obtained based on the first SOC difference, the second SOC difference, the temperature rise rate, the voltage drop rate, the warning frequency of heat-related fault types, and the second detection rule.

[0021] In one optional embodiment of this application, the second detection rule includes: a battery consistency detection rule and a thermal runaway index calculation rule; the second parameter includes: battery modules with poor consistency and thermal runaway index values;

[0022] The second parameter is obtained based on the first SOC difference, the second SOC difference, the temperature rise rate, the voltage drop rate, the warning frequency of heat-related fault types, and the second detection rule. Specifically, it includes:

[0023] Based on the first SOC difference, the second SOC difference, and the battery consistency detection rules, the battery modules with poor consistency are obtained;

[0024] Based on the rate of temperature rise, rate of voltage drop, warning frequency of thermal-related fault types, and calculation rules for thermal runaway indices, the thermal runaway index value of the target battery is obtained.

[0025] In one optional embodiment of this application, the battery consistency detection rules include: consistency difference judgment conditions and fault module determination rules;

[0026] Based on the first SOC difference, the second SOC difference, and the battery consistency detection rules, the battery modules with poor consistency are obtained, specifically including:

[0027] Based on the first SOC difference values ​​within the range from the first time point to the second time point, the trend of the first SOC difference value changing with time is obtained;

[0028] Determine whether the trend of change meets the criteria for poor consistency.

[0029] If the consistency difference judgment condition is met, then the battery module with the consistency difference is determined according to the difference of each second SOC within the range from the first time to the second time and the fault module determination rule.

[0030] In one optional embodiment of this application, the thermal runaway index value of the target battery is obtained based on the temperature rise rate, voltage drop rate, thermal-related fault type warning frequency, and thermal runaway index calculation rules, specifically including:

[0031] The thermal runaway index value is obtained based on the temperature rise rate, voltage drop rate, warning frequency of heat-related fault types, and the preset weights corresponding to the thermal runaway index calculation rules.

[0032] The preset weights are obtained based on the information entropy of historical data on the rate of temperature increase, the rate of voltage decrease, and the warning frequency of heat-related fault types.

[0033] In one alternative embodiment of this application, the target battery is applied to a new energy vehicle;

[0034] The method also includes:

[0035] The thermal runaway index value of the target battery and the operating condition data of the new energy vehicle are input into the thermal runaway index value prediction model to obtain the predicted value of the thermal runaway index of the target battery at the target future time.

[0036] Based on the predicted values ​​of thermal runaway indicators, early warning measures should be taken;

[0037] Among them, the thermal runaway index prediction model is trained based on historical thermal runaway index values ​​and historical operating condition data.

[0038] Secondly, embodiments of this application provide a battery status monitoring device, including:

[0039] The data acquisition module is used to acquire the operating data of the target battery; wherein, the operating data includes: time period operating data and current time period operating data; the time period operating data includes time period operating data within the range from the first time period to the second time period; the first time period is earlier than the second time period; the second time period is earlier than or equal to the current time period;

[0040] The data processing module is used to obtain the first indicator value corresponding to the first monitoring indicator based on the running data at a given time, and to obtain the second indicator value corresponding to the second monitoring indicator based on the running data at a given time period.

[0041] The parameter acquisition module is used to obtain the first parameter of the target battery according to the first index value and the first detection rule, and to obtain the second parameter according to the second index value, the first parameter time period sequence and the second detection rule; wherein, the first detection rule includes the mapping relationship between the first parameter and the threshold range of the first index value; the first parameter time period sequence includes the sequence of the first parameters corresponding to each time point from the first time point to the second time point;

[0042] The status monitoring module is used to determine the status information of the target battery based on the first parameter and / or the second parameter.

[0043] Thirdly, embodiments of this application provide an electronic device, which includes a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps of the battery status monitoring method provided in any of the above embodiments.

[0044] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the battery status monitoring method provided in any of the above embodiments.

[0045] The beneficial effects of the technical solutions provided in this application are:

[0046] By mining and analyzing the battery's operational data, the target battery's status is monitored from two dimensions: time and time period. The first indicator value is obtained from the number of operations at each time. The first parameter is obtained from the relationship between the first indicator value and the threshold range of the first indicator value in the first detection rule. The second monitoring value is obtained from the operational data of the time period. The second parameter is obtained from the second monitoring value, the time period sequence of the first parameter corresponding to that time period, and the second detection rule. The status information that can accurately reflect the battery's operating status is obtained from the first parameter and / or the second parameter, providing support for battery management and maintenance. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below.

[0048] Figure 1 A flowchart illustrating a battery status monitoring method provided in this application embodiment;

[0049] Figure 2 This is a schematic diagram of a method for obtaining a first parameter provided in an embodiment of this application;

[0050] Figure 3 This is a schematic diagram of a method for determining battery modules with poor consistency, provided in an embodiment of this application.

[0051] Figure 4 This is a schematic diagram illustrating a method for obtaining thermal runaway index values ​​provided in an embodiment of this application;

[0052] Figure 5 A flowchart illustrating a battery status monitoring method provided in an embodiment of this application;

[0053] Figure 6 This is a schematic diagram of the structure of a battery status monitoring device provided in an embodiment of this application;

[0054] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0055] The embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the embodiments described below with reference to the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions of the embodiments of this application.

[0056] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the terms “comprising” and “including” as used in embodiments of this application mean that the corresponding feature can be implemented as the presented feature, information, data, step, operation, element, and / or component, but do not exclude implementation as other features, information, data, step, operation, element, component, and / or combinations thereof supported by the art. It should be understood that when we say that an element is “connected” or “coupled” to another element, the one element can be directly connected or coupled to the other element, or it can mean that the one element and the other element establish a connection relationship through an intermediate element. Furthermore, “connected” or “coupled” as used herein can include wireless connection or wireless coupling. The term “and / or” as used herein indicates at least one of the items defined by the term; for example, “A and / or B” can be implemented as “A,” or as “B,” or as “A and B.”

[0057] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0058] The following explains the terminology and related technologies involved in this application:

[0059] According to statistics, new energy vehicles maintained high growth in 2022, with total sales reaching 6.884 million units, and domestic power battery installations reaching 294.58 GWh. Behind this high growth in power battery volume, the safety of power batteries has increasingly attracted public attention, and battery safety is one of the urgent issues that needs to be addressed as new energy vehicles move into a new stage of development.

[0060] Currently, lithium batteries are the most widely used type of power battery. Due to the unique properties of their constituent materials, they may trigger safety accidents under certain external conditions. Therefore, it is essential to take measures to reduce the likelihood of battery safety accidents and improve the safety of power batteries to lower the probability of such accidents.

[0061] Currently, common approaches focus on the battery's internal components, such as improving the performance of the positive and negative electrode materials and electrolyte materials, or optimizing the accident propagation design from a mechanical design perspective to reduce the severity of accidents.

[0062] Both of the above methods improve battery safety by designing the battery itself. However, after the battery is put into use, safety accidents can still be caused by factors such as the working environment and battery failure. Currently, there is no method to monitor battery safety.

[0063] To better manage and control battery systems, and to provide convenient installation and maintenance methods, thereby improving the performance and reliability of the entire battery system, batteries are now often used in the form of battery packs. A battery pack is assembled from one or more batteries, and the individual battery cells are the basic components of the battery pack.

[0064] The technical solutions of this application and their effects are described below through several exemplary embodiments. It should be noted that the following embodiments can be referenced, borrowed from, or combined with each other. Identical terms, similar features, and similar implementation steps in different embodiments will not be repeated.

[0065] This application provides a battery status monitoring method. The purpose of this application is to at least solve one of the above-mentioned technical defects. Optionally, this application can be applied to a terminal or a server. All steps in the method can be executed independently by the terminal or the server, or jointly by the terminal and the server.

[0066] The server can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server providing cloud computing services. The terminal (also known as a user terminal or user device) can be a smartphone, tablet, laptop, desktop computer, smart voice interaction device (such as a smart speaker), wearable electronic device (such as a smartwatch), in-vehicle terminal, smart home appliance (such as a smart TV), AR / VR device, etc., but is not limited to these.

[0067] The embodiments of this application will be described below with the vehicle-mounted terminal as the execution subject. However, this does not constitute a limitation on the embodiments of this application. In addition to the vehicle-mounted battery status monitoring scenario, the method provided by the embodiments of this application can also be applied to other scenarios for monitoring the battery status during battery use.

[0068] Figure 1 A flowchart of a battery status monitoring method provided in an embodiment of this application is shown below. Figure 1 As shown, the technical solution provided in this application includes the following steps:

[0069] Step S101: Obtain the operating data of the target battery.

[0070] Among them, operational data refers to various characteristic data describing the operating state and performance of the target battery, which may include voltage, current, temperature, state of charge (SOC) value, insulation resistance (R). 绝缘 The operating status (such as charging, discharging, or idle) can be understood to be based on the structural characteristics of the battery. The operating data can be the data of the target battery as a whole, the data of the individual battery cells, and the data of each monitoring point in the battery.

[0071] The operational data includes: time-period operational data and current-time operational data. Time-period operational data includes operational data within the range from the first time point to the second time point; the first time point is earlier than the second time point; the second time point is earlier than or equal to the current time point.

[0072] Specifically, taking the application of a battery pack (i.e., the target battery) in a new energy vehicle as an example, the Battery Management System (BMS) configured within the battery pack monitors the status of each individual battery cell, acquiring the voltage, current, temperature, SOC value, and R of each cell. 绝缘 The vehicle-mounted T-BOX (Telematics-BOX, vehicle networking control unit) acquires the data collected by the BMS and transmits the data to the vehicle terminal.

[0073] In addition to the terminal, the execution of step S101 can also be performed by a server. For example, after the vehicle T-BOX obtains the operating data of the target battery, it can also send the data to a server or other terminal, which will then execute subsequent steps.

[0074] Time-based operational data refers to data recorded at a specific moment or point in time. Time-period operational data, on the other hand, refers to data recorded over a period of time (usually a continuous time period). This embodiment monitors the battery's operational status comprehensively from both time-based and time-period dimensions; therefore, it acquires time-period operational data and time-based operational data at the current moment.

[0075] It is understandable that the time-period operation data does not necessarily include the operation data at the current moment. That is, the time period corresponding to the time-period operation data is the time period from the first moment to the second moment. The time-period operation data includes the time operation data of each moment within the above time period. The first moment is earlier than the second moment, and the second moment is earlier than or equal to the current moment. The specific settings of the first moment and the second moment can be determined according to actual needs.

[0076] For example, if the time period between the first and second moments is preset to one day, and the current moment is 3 PM today, the time period could be data from 3 PM yesterday (first moment) to 3 PM today (second moment), or data from 12 AM yesterday (first moment) to 12 AM yesterday (second moment). Generally, to ensure the timeliness and accuracy of the data, the time period can be set to the current moment or as close to the current moment as possible.

[0077] It should be noted that the method of obtaining the target battery's operating data can be real-time monitoring, timed sampling, or event triggering (such as real-time monitoring after determining that the set temperature threshold has been exceeded, or real-time monitoring after the new energy vehicle's operating time has exceeded the time threshold). The specific method and frequency can be determined according to the application scenario and actual needs. The time interval of each moment included in the time period operating data can also be determined according to actual needs, and this application does not limit it in this regard.

[0078] It is understood that the specific type of operational data acquired can be determined based on the different battery types and the actual needs of calculating indicator values, and the above examples are not intended to limit this application.

[0079] Step S102: Based on the time-based running data, obtain the first indicator value corresponding to the first monitoring indicator, and based on the time-period running data, obtain the second indicator value corresponding to the second monitoring indicator.

[0080] Specifically, based on the different needs of the two dimensions of time and time period, the first monitoring indicator is set in the time dimension, and the second monitoring indicator is set in the time period dimension.

[0081] The acquired operational data is preprocessed to obtain the first indicator value corresponding to the first monitoring indicator based on the operational data at different times, so as to facilitate real-time monitoring of the operational status. Based on the operational data for a specific time period, the second indicator value corresponding to the second monitoring indicator is obtained, so as to facilitate data mining and analysis within that time period and to monitor the changing trends of the operational status.

[0082] It is understandable that the specific types and quantities of the first and second monitoring indicators can be set according to actual needs. In addition, the first and second monitoring indicators can be of the same type.

[0083] For example, the first monitoring indicator can be set as the maximum and minimum voltage, maximum current, average temperature, temperature difference, and minimum SOC of each cell in the target battery. The second monitoring indicator can be a type of time-based information or a type of time-period information that reflects the changing trend of the operating status, such as the pressure difference, temperature difference, and SOC difference of each cell at each moment, as well as the rate of temperature change and rate of pressure change during that time period.

[0084] Step S103: Obtain the first parameter of the target battery according to the first index value and the first detection rule, and obtain the second parameter according to the second index value, the time period sequence of the first parameter and the second detection rule.

[0085] The first detection rule includes the mapping relationship between the first parameter and the threshold range of the first indicator value; the first parameter time period sequence includes the sequence of the first parameter corresponding to each time point from the first time point to the second time point.

[0086] Specifically, a first detection rule is preset based on a threshold in the time dimension, and a mapping relationship is set between the first parameter and the threshold range of the first indicator value. After determining the first indicator value, the corresponding first parameter can be determined based on the mapping relationship.

[0087] Understandably, the threshold can be a specific numerical value, or a derived relationship from the first monitoring indicator (e.g., if there are indicators A and B, the threshold range corresponding to the value of A could be 0.3B to 0.7B). Furthermore, the threshold range can be an open interval, a closed interval, or a semi-open interval, and can also be represented by an inequality.

[0088] In the second dimension, a statistical data model is used to pre-define a second detection rule to explore the correlation and trend of change between variables. The second parameter is obtained based on the second indicator value, the time series of the first parameter, and the second detection rule.

[0089] It is understandable that the first and second parameters can be in numerical, categorical, or text form, and the specific parameter type and its meaning can be set according to the specific application scenario and actual needs.

[0090] It should be noted that, in actual application of this embodiment, the second detection rule can be based on the second index value and the time series of the first parameter to establish a mathematical model for calculating the second parameter, and the corresponding value of the second parameter can be used to evaluate the battery operating status.

[0091] In addition, machine learning can be combined to design a neural network model. This model takes the second indicator value and the time series of the first parameter as input, the second parameter as output, and uses historical data as samples to train the model, so that the model can automatically learn and predict the second parameter. At this time, the second parameter output by the model can be a numerical value or a specific fault type, etc.

[0092] For example, the first parameter can be set to text type to indicate an abnormal first indicator value or a fault type. For instance, if the first indicator value is the maximum temperature, the first parameter could be "maximum temperature abnormal" or "battery high temperature". The second parameter can be set to numerical type, which is a value reflecting the battery status. For example, if the numerical range is set to 0-100%, the closer the second parameter is to 100%, the higher the probability of battery abnormality and the more likely safety problems will occur.

[0093] Step S104: Determine the state information of the target battery based on the first parameter and / or the second parameter.

[0094] Specifically, the state information of the target battery is determined based on the first parameter and / or the second parameter. It is understandable that the method of determining the state information based on the first and second parameters, as well as the format in which the state information is represented, can be set according to the specific application scenario and actual needs.

[0095] For example, the status information can be categorized to indicate the battery's operating state (including abnormal and normal). If the first parameter is "abnormal maximum temperature," then the target battery is determined to be in a high-temperature state, and the status information is abnormal. In addition, the status information can also include the type of fault that has occurred, the predicted type of fault, and the fault risk level.

[0096] It is understood that the method of monitoring the battery status using the two dimensions of time and time period in this application can be implemented individually or together. For example, during the use of the target battery, only the time dimension of status monitoring can be performed to obtain a first parameter, which is used to determine the status information. After the target battery is no longer used, the data from the time of disuse to the three hours prior to the time of disuse can be used to obtain a second parameter, which is used together with the first parameter corresponding to the time of disuse to determine the status information.

[0097] It should be noted that "first" and "second" are only used in the text to distinguish between monitoring indicators, indicator values, detection rules and parameters, and do not contain any actual meaning.

[0098] The technical solution provided in this application provides a multi-dimensional battery monitoring method that is timely, accurate, and has broad coverage. It utilizes the mining and analysis of battery operation data to monitor the target battery's status from two dimensions: time and time period. The method obtains a first indicator value based on the number of operations at each time point. A first parameter is obtained based on the relationship between the first indicator value and the threshold range of the first indicator value in a first detection rule. A second monitoring value is obtained based on the operation data within a time period. A second parameter is obtained based on the second monitoring value, the corresponding first parameter time period sequence, and the second detection rule. The first parameter and / or the second parameter together provide status information that comprehensively considers the instantaneous situation and long-term trend of battery operation, accurately reflecting the battery's operating status. This provides support for battery management and maintenance, enabling early detection of battery risks, timely intervention, and prevention of risk deterioration and expansion, thereby reducing losses and improving the safety of battery use and enhancing user experience.

[0099] In one optional embodiment of this application, it further includes:

[0100] Determine whether the status information meets the warning conditions;

[0101] If the conditions for issuing an early warning are met, then early warning measures will be taken.

[0102] Specifically, after obtaining the status information, it is determined whether the status information meets the warning conditions. Based on the judgment result, it is determined whether to take warning measures. If it is determined that the warning conditions are met, warning measures are taken; otherwise, no warning is issued.

[0103] Understandably, the specific types of status information, warning conditions, and warning measures, as well as the relationships between them, can be set according to actual application scenarios and actual needs.

[0104] The status information indicates that the battery is at a high temperature and exceeds xx℃, or the status information indicates an abnormality, such as battery overcharging. Warning measures can include sending warning messages (voice warnings, display warnings, etc.) and taking intervention measures (such as activating heat dissipation devices, cooling devices, undervoltage protection devices, and overvoltage protection devices) to remind relevant personnel to handle abnormal situations promptly and intervene in a timely manner to prevent safety issues from occurring.

[0105] For example, the status information is categorized by dimension. When the status information corresponding to the first parameter meets the warning conditions, corresponding intervention measures are taken while sending a voice warning message. For instance, if the battery is overheating, a voice announcement is made to the driver stating, "Battery temperature is too high; emergency stop recommended," and the cooling system is activated to cool the battery. When the status information corresponding to the second parameter meets the warning conditions, only a display warning message is sent. For example, if it is determined that the battery has been used for a long time and the safety risk is too high, "Battery replacement recommended" is displayed on the vehicle's screen.

[0106] The technical solution provided in this application takes early warning measures after determining that the status information meets the early warning conditions. This can detect abnormal battery status in a timely and effective manner. By taking corresponding early warning measures, it can facilitate targeted maintenance, priority management, and preventive maintenance, and curb the deterioration and expansion of risks, thereby further improving the safety and reliability of battery use and providing support for battery management and maintenance.

[0107] In one optional embodiment of this application, the first parameter of the target battery is obtained according to the first index value and the first detection rule, specifically including:

[0108] Based on the first indicator value and the first detection rule, determine the target fault type of the target battery and the target warning level corresponding to the target fault type;

[0109] The first parameter is obtained based on the target fault type and the target warning level.

[0110] Specifically, the first indicator value can be one or more indicator values, and the first detection rule can be one or more judgment conditions, used to determine the target fault type and the target warning level corresponding to the target fault type based on the first indicator value and a preset threshold range, and to obtain the first parameter based on the target fault type and the target warning level.

[0111] For example, Figure 2 This is a schematic diagram of a method for obtaining a first parameter provided in an embodiment of this application, as shown below. Figure 2 As shown, based on data cleaning, mining, and analysis of a large amount of battery operation data, and in conjunction with battery type and national standards, the first monitoring indicator and the first detection rule are set.

[0112] The first monitoring indicator may include the maximum voltage (V) of the individual cells in the target battery. max The minimum voltage V min Pressure difference ΔV (i.e., voltage range), total voltage U sum The maximum temperature T max Minimum temperature T min Average temperature T avg Temperature difference ΔT (i.e., temperature range), R 绝缘The SOC value corresponding to the lowest voltage. min The SOC value corresponding to the highest voltage. max SOC difference ΔSOC (i.e. SOC range).

[0113] Based on the impact of the fault on the degree of use, three warning levels are set for each fault type, as shown in Table 1:

[0114] Table 1

[0115]

[0116] The fault types, battery types, first detection rules, and warning levels involved in this embodiment are shown in Table 2. The first parameter threshold range is expressed in the form of an inequality threshold range.

[0117] Table 2

[0118]

[0119]

[0120] After acquiring the target battery's operational data, a data cleaning algorithm is used to filter out invalid and abnormal data, resulting in a true and valid first indicator value. Based on the first detection rules in Table 2, it is determined whether the first indicator value meets the threshold ranges specified in the first detection rules, thus identifying the target fault type and its corresponding warning level. It is understood that there may be more than one target fault type. The first parameter can be directly the fault type and warning level, or it can be in the form of a fault type code and a warning level code, etc., depending on actual needs.

[0121] It is understood that the warning levels and warning measures in this application may include fault warnings before a fault occurs (such as level one and level two), or fault alarms after a fault has occurred (such as level three). Correspondingly, different warning measures can be set for different levels and actual situations.

[0122] The technical solution provided in this application determines the target fault type and the corresponding target warning level of the target battery based on the first index value and the first detection rule, and obtains the first parameter based on the target fault type and the target warning level to set the fault type and fault level. This can more accurately reflect the operating status and actual fault risk of the target battery, so as to facilitate targeted warning or intervention, reduce safety risks, and provide support for battery management and maintenance.

[0123] In one optional embodiment of this application, the second parameter is obtained based on the second index value, the first parameter time period sequence, and the second detection rule, specifically including:

[0124] Based on the second index value, the first state of charge (SOC) difference and the second SOC difference, the temperature rise rate and the voltage drop rate are obtained; wherein, the target battery includes at least one battery module; the first SOC difference is the absolute value of the difference between the average SOC value and the minimum SOC value of each battery module; the second SOC difference is the absolute value of the difference between the SOC correction value of each battery module and the average SOC value.

[0125] Based on the time period sequence of the first parameter, the warning frequency of heat-related fault types is obtained;

[0126] The second parameter is obtained based on the first SOC difference, the second SOC difference, the temperature rise rate, the voltage drop rate, the warning frequency of heat-related fault types, and the second detection rule.

[0127] Specifically, based on the analysis of operational data, the second monitoring indicator required to obtain the second parameter is determined. After filtering out some invalid and abnormal data through data cleaning algorithms, the true and valid data stream is obtained, resulting in the second indicator value. The second indicator value is used to calculate the first SOC difference, the second SOC difference, the temperature rise rate, and the voltage drop rate.

[0128] It is understood that, since the battery pack is assembled from one or more battery modules, the target battery in this application includes at least one battery module (i.e., battery pack), and the operating data of each battery module at each time can be obtained to obtain a second index value.

[0129] For example, the second monitoring metrics include SOC value, temperature, and voltage.

[0130] For a target battery consisting of k battery modules, the SOC correction value (i.e., the actual battery capacity) of the m-th battery module is... 修正,m The calculation method is as follows:

[0131]

[0132]

[0133] ΔSOC′=|SOC 平均 -SOC min |

[0134] ΔSOC m =|SOC 修正,m -SOC 平均 |

[0135] The first SOC difference ΔSOC′ is SOC 平均 With SOC minThe absolute value of the difference, the second SOC difference ΔSOC″ is the absolute value of the difference between the SOC correction value of each battery module and the SOC mean. ΔSOC′ can be used to quantify the battery consistency trend, and ΔSOC″ can be used to determine the location of the battery module that causes poor battery consistency.

[0136] It is understandable that the SOC of the m-th battery module... 修正,m With SOC 平均 The absolute value of the difference is denoted as ΔSOC. m The ΔSOC″ at each moment is the ΔSOC of all (k) battery modules at that moment. m Sequence (the sequence includes ΔSOC1-ΔSOC) k ).

[0137] Among them, SOC min The minimum SOC is calculated based on the minimum voltage. max The SOC is the maximum value calculated based on the maximum voltage. 平均 This is the average SOC value calculated based on the average voltage.

[0138] Calculate the rate of temperature rise (i.e., the rate of temperature rise T) based on the voltage and temperature values ​​at each moment. r ) and voltage drop rate (i.e., voltage drop rate V) r ).

[0139]

[0140]

[0141] Among them, T n and T n-1 V represents the temperature values ​​at time n and time n-1, respectively. n and V n-1 These represent the voltage values ​​at time n and time n-1, respectively.

[0142] Understandably, the temperature and voltage values ​​at each moment can be selected from the maximum value, the average value, or the value taken at a certain monitoring point. Additionally, the temperature rise rate T... r and pressure drop rate V r It can be the instantaneous rate determined according to the changes between each moment, or it can be the average rate over a period of time, which can be determined according to actual needs.

[0143] Based on the time period sequence of the first parameter, the frequency of occurrence of heat-related fault types can be determined, and the warning frequency of heat-related fault types can be further obtained. It is understandable that the specific fault types and quantities can be determined according to actual needs. Furthermore, based on the determined warning levels, the warning frequency of a specific warning level can be considered selectively.

[0144] Based on the first SOC difference, the second SOC difference, the rate of temperature increase, the rate of voltage decrease, the warning frequency of thermal-related fault types, and the second detection rule, the operating status of the target battery in the time period dimension is analyzed to obtain the second parameter.

[0145] It should be noted that "first" and "second" are only used to distinguish the SOC difference in the text and do not contain any actual meaning.

[0146] The technical solution provided in this application combines the first SOC difference, the second SOC difference, the temperature rise rate, the voltage drop rate, the warning frequency of thermally related fault types, and the second detection rule to determine the second parameter. The second parameter is used to monitor the battery status in a time period dimension, so that the second parameter can reflect the imbalance between battery modules in the target battery and thermally related characteristics, and promptly detect abnormal conditions or potential faults of battery modules, thereby taking corresponding maintenance or repair measures to ensure the reliability and safety of the target battery and monitor and maintain the normal operation of the battery.

[0147] In one optional embodiment of this application, the second detection rule includes: a battery consistency detection rule and a thermal runaway index calculation rule; the second parameter includes: battery modules with poor consistency and thermal runaway index values;

[0148] The second parameter is obtained based on the first SOC difference, the second SOC difference, the temperature rise rate, the voltage drop rate, the warning frequency of heat-related fault types, and the second detection rule. Specifically, it includes:

[0149] Based on the first SOC difference, the second SOC difference, and the battery consistency detection rules, the battery modules with poor consistency are obtained;

[0150] Based on the rate of temperature rise, rate of voltage drop, warning frequency of thermal-related fault types, and calculation rules for thermal runaway indices, the thermal runaway index value of the target battery is obtained.

[0151] Specifically, the time-period dimension mainly focuses on assessing and warning of potential battery risks, which can be divided into assessing the consistency of the target battery and assessing the risk of thermal runaway. Correspondingly, the second detection rules include: battery consistency detection rules and thermal runaway index calculation rules; the second parameters include: battery modules with poor consistency and thermal runaway index values.

[0152] For battery packs, inconsistencies between individual cells can lead to overcharging or over-discharging of certain cells. Overcharging has a significant impact on battery packs, affecting not only their lifespan and performance but also posing substantial safety hazards.

[0153] The consistency of the battery is evaluated based on the first SOC difference, the second SOC difference, and the battery consistency detection rules. If the battery consistency is determined to be poor, then the battery module with poor consistency is identified.

[0154] Based on the rate of temperature rise, rate of voltage drop, warning frequency of thermal-related fault types, and calculation rules for thermal runaway index, the thermal runaway index value of the target battery is calculated.

[0155] It is understandable that battery consistency can be determined based on the changes in the first and second SOC differences. Specific methods for this determination include expert analysis, machine learning, and mathematical modeling. Furthermore, the calculation rules for thermal runaway indicators can be based on relevant statistical data models or neural network models. The specific method can be determined according to actual needs.

[0156] The second parameter in the technical solution provided in this application includes a battery module with poor consistency and a thermal runaway index value. The battery module with poor consistency reflects the inconsistencies existing in the battery pack, while the thermal runaway index value reflects the risk of thermal runaway of the battery. By reflecting the operating status of the battery over a specific time period through the second parameter, abnormal conditions or potential faults of the battery module can be detected in a timely manner, thereby enabling corresponding maintenance or repair measures to be taken to ensure the reliability and safety of the target battery and to monitor and maintain the normal operation of the battery.

[0157] In one optional embodiment of this application, the battery consistency detection rules include: consistency difference judgment conditions and fault module determination rules;

[0158] Based on the first SOC difference, the second SOC difference, and the battery consistency detection rules, the battery modules with poor consistency are obtained, specifically including:

[0159] Based on the first SOC difference values ​​within the range from the first time point to the second time point, the trend of the first SOC difference value changing with time is obtained;

[0160] Determine whether the trend of change meets the criteria for poor consistency.

[0161] If the consistency difference judgment condition is met, then the battery module with the consistency difference is determined according to the difference of each second SOC within the range from the first time to the second time and the fault module determination rule.

[0162] Specifically, Figure 3 This is a schematic diagram of a method for determining battery modules with poor consistency provided in an embodiment of this application, as shown below. Figure 3 As shown, the battery consistency detection rules include: consistency difference judgment conditions and fault module determination rules. Determining the battery module with poor consistency is divided into two steps: consistency difference judgment and fault module determination.

[0163] After going through multiple steps such as data acquisition, data cleaning, and calculation of the second indicator value (SOC value), the first SOC difference and the second SOC difference of each battery module are calculated.

[0164] The differences in the first SOC values ​​at different times within the range from the first time to the second time can form a time-based sequence. Based on the difference in the first SOC values ​​before and after the sequence, the trend of the first SOC difference over time can be obtained.

[0165] The consistency difference judgment refers to judging whether the trend of change meets the consistency difference judgment condition. If it is determined that the difference value generally shows an increasing trend, then the overall consistency of the target battery shows a deteriorating trend.

[0166] If the consistency poor judgment condition is met (i.e., the overall consistency of the target battery shows a deteriorating trend), then the battery module with poor consistency is determined according to the difference of each second SOC within the range from the first time to the second time and the fault module determination rule.

[0167] It is understandable that "fault module identification" refers to identifying modules with poor battery consistency. This can be understood as filtering outliers based on the second SOC difference (identified ΔSOC). m Outliers in the sequence can be used to identify abnormal battery modules. Outlier screening methods include the 3σ (three standard deviations) method, box plot method, and Z-score method.

[0168] For example, the principle behind using 3σ to filter outliers is as follows:

[0169]

[0170] Where, x m Indicates ΔSOC m , This represents the second SOC difference (ΔSOC) m The mean of the sequence. When x m If the value falls within (-∞, -3σ] or [3σ, +∞), it is considered an outlier. The location of the module with poor consistency is determined based on the outlier.

[0171] It is understandable that the number of battery modules with poor consistency can be determined according to the actual situation. In addition, the location of the individual battery cells in the battery modules with poor consistency can be further determined.

[0172] The technical solution provided in this application can help ensure the performance of the target battery, extend its lifespan, improve safety, and optimize energy utilization and efficiency by determining whether the target battery has poor consistency and identifying the location of the poorly consistent battery module, thereby further improving the reliability and safety of the target battery.

[0173] In one optional embodiment of this application, the thermal runaway index value of the target battery is obtained based on the temperature rise rate, voltage drop rate, thermal-related fault type warning frequency, and thermal runaway index calculation rules, specifically including:

[0174] The thermal runaway index value is obtained based on the temperature rise rate, voltage drop rate, warning frequency of heat-related fault types, and the preset weights corresponding to the thermal runaway index calculation rules.

[0175] The preset weights are obtained based on the information entropy of historical data on the rate of temperature increase, the rate of voltage decrease, and the warning frequency of heat-related fault types.

[0176] Specifically, the risk of thermal runaway in batteries can be divided into abrupt internal short circuits and evolving internal short circuits. Abrupt internal short circuits are difficult to predict in advance through data monitoring. Evolving internal short circuits, on the other hand, have clear data characteristics, manifesting as an increase in temperature and a decrease in voltage.

[0177] This embodiment constructs a thermal protection index (TPI) to assess the likelihood of an evolved internal short-circuit thermal runaway in the battery.

[0178] Figure 4 This is a schematic diagram illustrating a method for obtaining thermal runaway index values ​​provided in an embodiment of this application, as shown below. Figure 4 As shown, when calculating the thermal runaway index value according to the thermal runaway index calculation rules, it is necessary to comprehensively consider the correlation and importance among the characteristic indicators (temperature rise rate, voltage drop rate, and warning frequency of thermal-related fault types), assign weights to each characteristic indicator, determine the corresponding preset weights, and perform weighted summation based on the corresponding preset weights to determine the thermal runaway index value, so that the thermal runaway index value can more accurately reflect the battery's operating state related to thermal runaway tendency.

[0179] The preset weights are derived from the information entropy of historical data on the rate of temperature increase, rate of voltage decrease, and frequency of warnings for heat-related fault types. Information entropy is typically used to describe the average amount of information generated by the entire random distribution. It has stronger statistical properties, can capture the distribution and variation patterns of various characteristic indicators using historical data, and comprehensively considers the correlation of features, thereby improving the accuracy and reliability of thermal runaway warnings. In practical applications, appropriate methods can be selected to calculate the preset weights and thermal runaway indicator values ​​based on specific circumstances.

[0180] For example, the method of using information entropy to calculate preset weights can be the entropy weight method, etc., and then the thermal runaway index value can be determined based on each feature index and preset weight (such as using a weighted fusion method to calculate the thermal runaway index value).

[0181] In addition, machine learning can be combined to design neural network models, using feature indicators as model inputs, thermal runaway index values ​​as model outputs, historical data as model samples, and loss functions designed based on information entropy. The model is then trained based on the loss function, enabling the model to automatically learn and determine the preset weights corresponding to the feature indicators, thus allowing the model to better learn the distribution patterns of the data.

[0182] For example, with a temperature rise rate T r Voltage drop rate V r Thermal-related fault type warning frequency (real-time alarm undervoltage fault occurrence frequency UV) n Overheating causes frequent UT failures n Temperature difference fault frequency TD n Based on this, the TPI formula corresponding to the thermal runaway index calculation rule is constructed as follows:

[0183] TPI = w1T r +w2V r +w3UV n +w4UT n +w5TD n

[0184] Among them, w1…w5 represent the preset weights of each feature index.

[0185] Understandably, the specific types and number of warning frequencies for heat-related fault types can be determined according to actual needs. For example, the warning frequency for heat-related fault types can be set as the average of the fault frequencies of multiple fault types.

[0186] Additionally, it should be noted that due to the temperature rise rate T r and pressure drop rate V r The sum can be an instantaneous value or a mean within a time period. The thermal runaway index value can also be a sequence of index values ​​within a time period or a mean representing the characteristics of the time period.

[0187] The steps for determining the weight values ​​of w1…w5 by calculating the information entropy values ​​of each indicator using the entropy weight method are as follows:

[0188] First, the values ​​of each characteristic index are normalized and standardized. The standardized calculation is as follows:

[0189] Positive indicators:

[0190] Negative indicators:

[0191] Where i = 1, ..., a, j = 1, ..., b, a is the observation period (i.e., the historical data corresponding to a time points), b is the number of feature indicators (b is 5 in this embodiment), x ijLet j be the value of the feature index in the i-th set of historical data. It is the standardized value of the j-th feature index in the i-th set of historical data.

[0192] Calculate the variation index: Calculate the proportion of the j-th index at time i, which is the overall variation magnitude p of the index. ij Calculation:

[0193]

[0194] Calculate the information entropy: Calculate the information entropy of each indicator, where the information entropy e of the j-th indicator is... j for:

[0195]

[0196] Information entropy redundancy: The information entropy redundancy g of the j-th index j for:

[0197] g j =1-e j

[0198] The preset weights for the feature indicators are: the weight w of the j-th indicator is calculated using information entropy. j for:

[0199]

[0200] By substituting the TPI formula with preset weights and specific values, the thermal runaway index value is calculated. The risk threshold value can be determined based on the actual performance of the thermal runaway index value to determine whether the battery has a thermal runaway risk and the level of risk.

[0201] The technical solution provided in this application can assess the safety of a target battery through thermal runaway index values, provide early warning of potential thermal runaway events, and offer timely information and decision-making basis for relevant parties. If the target battery has a high risk of thermal runaway, corresponding early warning measures can be taken in a timely manner to reduce the risk of thermal runaway, thereby reducing the possibility and impact of accidents, ensuring the safe operation of the battery, and further improving battery safety and reliability.

[0202] In one optional embodiment of this application, the target battery is applied to a new energy vehicle; the method further includes:

[0203] The thermal runaway index value of the target battery and the operating condition data of the new energy vehicle are input into the thermal runaway index value prediction model to obtain the predicted value of the thermal runaway index of the target battery at the target future time.

[0204] Based on the predicted values ​​of thermal runaway indicators, early warning measures should be taken;

[0205] Among them, the thermal runaway index prediction model is trained based on historical thermal runaway index values ​​and historical operating condition data.

[0206] Specifically, for the target battery used in new energy vehicles, in order to ensure its safety and reliability, a thermal runaway index prediction model can be constructed based on the calculated thermal runaway index value, thus adding a method for predicting and warning of the thermal runaway index value.

[0207] The thermal runaway index prediction model is trained based on historical thermal runaway index values ​​and historical operating condition data. Operating condition data refers to data that records various parameters and states of the vehicle during operation, including vehicle speed, mileage, types and number of failures, battery life and charge / discharge cycle count, etc.

[0208] Understandably, the types and quantities of operating conditions, as well as the structure and training methods of the prediction model, can be determined according to actual needs.

[0209] The thermal runaway index values ​​of the target battery and the operating condition data of the new energy vehicle are input into the thermal runaway index prediction model to obtain the predicted thermal runaway index values ​​of the target battery at the target future time. It is understandable that the time difference between the target future time and the current time can be determined according to actual needs during model training.

[0210] Based on the predicted values ​​of thermal runaway indicators, early warning measures can be taken. For example, if the predicted value exceeds the safety threshold, an alarm can be triggered or vehicles with a high risk of thermal runaway can be added to a priority monitoring list to prevent thermal runaway events from occurring.

[0211] The technical solution provided in this application constructs a thermal runaway index based on battery operating data to assess and warn of potential thermal risks to the battery. Furthermore, it incorporates a method for predicting and warning of thermal runaway index values ​​by combining operating data from new energy vehicles. The thermal runaway index value prediction model predicts future thermal runaway index values, enabling early prediction of thermal risks in new energy vehicle batteries. This allows for timely implementation of safety measures, effectively preventing thermal runaway events and ensuring the safe operation of new energy vehicles. It also achieves real-time monitoring and early warning of battery thermal risks.

[0212] The following specific example will further illustrate the detailed application of the solution in this application:

[0213] This embodiment comprehensively identifies battery safety risks from two dimensions and takes timely maintenance intervention measures to reduce the probability of battery safety accidents. The first dimension is to monitor the battery's health status in real time based on data sent from the vehicle's T-BOX. The second dimension is to diagnose potential battery safety risks based on historical battery data.

[0214] Figure 5 This is a flowchart illustrating a battery state monitoring method provided in an embodiment of this application, as shown below. Figure 5 As shown, the system acquires the real-time operating data stream of the target battery, performs data cleaning to determine the authenticity, validity, and completeness of the real-time data stream, including handling invalid and outlier values, data format processing, state calculation, battery type calculation, and the calculation of derived indicators (first monitoring indicator and second monitoring indicator), and outputs the first indicator value and the second indicator value.

[0215] The real-time monitoring and alarm system is used to determine the threshold range that the first indicator value meets based on the first indicator value and the first detection rule, determine the target fault type and target fault level, obtain and store the first parameter, and take early warning measures based on the first parameter.

[0216] For example, the first parameter is set as fault type and warning level. In order to eliminate false alarms caused by incomplete data cleaning, the triggering of warning measures is restricted. Warning measures are only taken if the number of triggering a single alarm is ≥2 (that is, the same fault type warning is triggered at least twice in a row).

[0217] Each piece of original information and alarm information that triggers the early warning measures will be stored in the database as part of the data support for the assessment and early warning of potential battery risks.

[0218] The potential risk assessment and early warning system acquires offline monitoring data at 24:00 every day, selects and calculates data, obtains the early warning frequency of heat-related fault types based on the time period sequence of the first parameter of the day, and obtains the first SOC difference and the second SOC difference, the temperature rise rate and the voltage drop rate based on the second index value.

[0219] Battery consistency is assessed based on the first SOC difference and the second SOC difference to identify battery modules with poor consistency. Thermal runaway risk is assessed based on the rate of temperature rise, rate of voltage drop, and frequency of warnings for heat-related fault types, and thermal runaway index values ​​are calculated.

[0220] Early warning measures are taken based on the first parameter (target fault type and target fault level) and / or the second parameter (battery modules with poor consistency and thermal runaway index values).

[0221] It is understood that the technical approach of storing data in the database in this embodiment includes data access, data storage, cleaning and calculation, battery status monitoring and early warning, storage and control, and user layer.

[0222] With the rapid development of data science, the value of data is becoming increasingly apparent. This embodiment, from a data science perspective, leverages big data platforms and data mining technologies to deeply analyze battery operation data. It provides comprehensive monitoring of battery operation safety from two dimensions: monitoring and alarming for common battery faults, and assessing and warning of potential battery risks. Timely warnings are issued when battery data shows abnormal changes, allowing for intervention measures to effectively improve battery efficiency, reduce the severity of battery safety accidents, and minimize losses.

[0223] Figure 6 This is a schematic diagram of the structure of a battery status monitoring device provided in an embodiment of this application, as shown below. Figure 6 As shown, the battery status monitoring device 60 includes:

[0224] The data acquisition module 601 is used to acquire the operating data of the target battery; wherein, the operating data includes: time period operating data and current time period operating data; the time period operating data includes time period operating data within the range from a first time period to a second time period; the first time period is earlier than the second time period; the second time period is earlier than or equal to the current time period;

[0225] The data processing module 602 is used to obtain the first indicator value corresponding to the first monitoring indicator based on the running data at a given time, and to obtain the second indicator value corresponding to the second monitoring indicator based on the running data at a given time period.

[0226] The parameter acquisition module 603 is used to obtain the first parameter of the target battery according to the first index value and the first detection rule, and to obtain the second parameter according to the second index value, the first parameter time period sequence and the second detection rule; wherein, the first detection rule includes the mapping relationship between the first parameter and the threshold range of the first index value; the first parameter time period sequence includes the sequence of the first parameters corresponding to each time point from the first time point to the second time point;

[0227] The status monitoring module 604 is used to determine the status information of the target battery based on the first parameter and / or the second parameter.

[0228] The technical solution provided in this embodiment monitors the status of the target battery from two dimensions: time and time period, by mining and analyzing the battery's operating data. A first indicator value is obtained from the number of times the battery operates. A first parameter is obtained from the relationship between the first indicator value and the threshold range of the first indicator value in the first detection rule. A second monitoring value is obtained from the operating data of the time period. A second parameter is obtained based on the second monitoring value, the time period sequence of the first parameter corresponding to the time period, and the second detection rule. Status information that can accurately reflect the battery's operating status is obtained from the first parameter and / or the second parameter, providing support for battery management and maintenance.

[0229] The apparatus in this application embodiment can execute the method provided in this application embodiment, and the implementation principle is similar. The actions performed by each module in the apparatus of each embodiment of this application correspond to the steps in the method of each embodiment of this application. For detailed functional descriptions of each module of the apparatus, please refer to the descriptions in the corresponding methods shown above, which will not be repeated here.

[0230] In one optional embodiment of this application, it further includes: a status warning module;

[0231] The status warning module is used to determine whether the status information meets the warning conditions;

[0232] If the conditions for issuing an early warning are met, then early warning measures will be taken.

[0233] In one optional embodiment of this application, the parameter acquisition module is specifically used for:

[0234] Based on the first indicator value and the first detection rule, determine the target fault type of the target battery and the target warning level corresponding to the target fault type;

[0235] The first parameter is obtained based on the target fault type and the target warning level.

[0236] In one optional embodiment of this application, the parameter acquisition module is specifically used for:

[0237] Based on the second index value, the first state of charge (SOC) difference and the second SOC difference, the temperature rise rate and the voltage drop rate are obtained; wherein, the target battery includes at least one battery module; the first SOC difference is the absolute value of the difference between the average SOC value and the minimum SOC value of each battery module; the second SOC difference is the absolute value of the difference between the SOC correction value of each battery module and the average SOC value.

[0238] Based on the time period sequence of the first parameter, the warning frequency of heat-related fault types is obtained;

[0239] The second parameter is obtained based on the first SOC difference, the second SOC difference, the temperature rise rate, the voltage drop rate, the warning frequency of heat-related fault types, and the second detection rule.

[0240] In one optional embodiment of this application, the second detection rule includes: a battery consistency detection rule and a thermal runaway index calculation rule; the second parameter includes: battery modules with poor consistency and thermal runaway index values;

[0241] The parameter acquisition module is specifically used for:

[0242] Based on the first SOC difference, the second SOC difference, and the battery consistency detection rules, the battery modules with poor consistency are obtained;

[0243] Based on the rate of temperature rise, rate of voltage drop, warning frequency of thermal-related fault types, and calculation rules for thermal runaway indices, the thermal runaway index value of the target battery is obtained.

[0244] In one optional embodiment of this application, the battery consistency detection rules include: consistency difference judgment conditions and fault module determination rules;

[0245] The parameter acquisition module is specifically used for:

[0246] Based on the first SOC difference values ​​within the range from the first time point to the second time point, the trend of the first SOC difference value changing with time is obtained;

[0247] Determine whether the trend of change meets the criteria for poor consistency.

[0248] If the consistency difference judgment condition is met, then the battery module with the consistency difference is determined according to the difference of each second SOC within the range from the first time to the second time and the fault module determination rule.

[0249] In one optional embodiment of this application, the parameter acquisition module is specifically used for:

[0250] The thermal runaway index value is obtained based on the temperature rise rate, voltage drop rate, warning frequency of heat-related fault types, and the preset weights corresponding to the thermal runaway index calculation rules.

[0251] The preset weights are obtained based on the information entropy of historical data on the rate of temperature increase, the rate of voltage decrease, and the warning frequency of heat-related fault types.

[0252] In one optional embodiment of this application, the target battery is applied to a new energy vehicle; the device further includes: an indicator prediction module;

[0253] The index prediction module is used to input the thermal runaway index value of the target battery and the operating condition data of the new energy vehicle into the thermal runaway index prediction model to obtain the predicted value of the thermal runaway index of the target battery at the target future time.

[0254] Based on the predicted values ​​of thermal runaway indicators, early warning measures should be taken;

[0255] Among them, the thermal runaway index prediction model is trained based on historical thermal runaway index values ​​and historical operating condition data.

[0256] This application provides an electronic device, including a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps of the battery status monitoring method described above. Compared with related technologies, it can achieve the following: by mining and analyzing the battery's operating data, the target battery's status is monitored from two dimensions: time and time period. A first indicator value is obtained from the time-based operating data. A first parameter is obtained based on the relationship between the first indicator value and the threshold range of the first indicator value in the first detection rule. A second monitoring value is obtained from the time-period operating data. A second parameter is obtained based on the second monitoring value, the time period sequence of the first parameter corresponding to the time period, and the second detection rule. Status information that can accurately reflect the battery's operating status is obtained using the first parameter and / or the second parameter, providing support for battery management and maintenance.

[0257] In one alternative embodiment, an electronic device is provided. Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 7 As shown, the electronic device 70 includes a processor 701 and a memory 703. The processor 701 and the memory 703 are connected, for example, via a bus 702. Optionally, the electronic device 70 may further include a transceiver 704, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 704 is not limited to one type, and the structure of the electronic device 70 does not constitute a limitation on the embodiments of this application.

[0258] Processor 701 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 701 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0259] Bus 702 may include a pathway for transmitting information between the aforementioned components. Bus 702 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 702 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 7 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0260] The memory 703 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium capable of carrying or storing computer programs and capable of being read by a computer, without limitation herein.

[0261] The memory 703 stores computer programs that execute embodiments of this application, and the processor 701 controls their execution. The processor 701 executes the computer programs stored in the memory 703 to implement the steps shown in the foregoing method embodiments.

[0262] The electronic devices in this application embodiment may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (e.g., vehicle navigation terminals), wearable devices, and fixed terminals such as digital TVs and desktop computers.

[0263] This application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it can implement the steps and corresponding content of the aforementioned method embodiments.

[0264] It should be noted that the computer-readable storage medium described above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0265] In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0266] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0267] The terms "first," "second," "third," "fourth," "1," "2," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in a sequence other than that shown in the figures or text.

[0268] It should be understood that although arrows indicate various operation steps in the flowcharts of this application's embodiments, the order in which these steps are implemented is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of this application's embodiments, the implementation steps in each flowchart can be executed in other orders as required. Furthermore, some or all steps in each flowchart, based on the actual implementation scenario, may include multiple sub-steps or multiple stages. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage can also be executed at different times. In scenarios where execution times differ, the execution order of these sub-steps or stages can be flexibly configured according to requirements, and this application's embodiments do not limit this.

[0269] The above description is only an optional implementation method for some implementation scenarios of this application. It should be noted that for those skilled in the art, other similar implementation methods based on the technical concept of this application without departing from the technical concept of this application also fall within the protection scope of the embodiments of this application.

Claims

1. A battery status monitoring method, characterized in that, include: Acquire the operating data of the target battery; wherein, the operating data includes: time period operating data and current time period operating data; the time period operating data includes time period operating data within the range from a first time period to a second time period; the first time period is earlier than the second time period; the second time period is earlier than or equal to the current time period; Based on the running data at the specified time, a first indicator value corresponding to the first monitoring indicator is obtained, and based on the running data during the specified time period, a second indicator value corresponding to the second monitoring indicator is obtained. The first parameter of the target battery is obtained based on the first indicator value and the first detection rule, and the second parameter is obtained based on the second indicator value, the first parameter time period sequence, and the second detection rule; wherein, the first detection rule includes the mapping relationship between the first parameter and the threshold range of the first indicator value; the first parameter time period sequence includes the sequence of the first parameter corresponding to each time point from the first time point to the second time point; The state information of the target battery is determined based on the first parameter and / or the second parameter; The process of obtaining the second parameter based on the second indicator value, the first parameter time period sequence, and the second detection rule specifically includes: Based on the second index value, the first state of charge (SOC) difference and the second SOC difference, the temperature rise rate and the voltage drop rate are obtained; wherein, the target battery includes at least one battery module; the first SOC difference is the absolute value of the difference between the average SOC value and the minimum SOC value of each battery module; the second SOC difference is the absolute value of the difference between the SOC correction value of each battery module and the average SOC value; Based on the time period sequence of the first parameter, the warning frequency of heat-related fault types is obtained; The second parameter is obtained based on the first SOC difference, the second SOC difference, the temperature rise rate, the voltage drop rate, the thermal-related fault type warning frequency, and the second detection rule; The second detection rule includes: battery consistency detection rule and thermal runaway index calculation rule; the second parameter includes: battery modules with poor consistency and thermal runaway index value; The second parameter is obtained based on the first SOC difference, the second SOC difference, the temperature rise rate, the voltage drop rate, the thermally related fault type warning frequency, and the second detection rule, specifically including: The battery module with poor consistency is obtained based on the first SOC difference, the second SOC difference, and the battery consistency detection rule; The thermal runaway index value of the target battery is obtained based on the temperature rise rate, the voltage drop rate, the warning frequency of the thermal-related fault type, and the thermal runaway index calculation rules.

2. The battery status monitoring method according to claim 1, characterized in that, Also includes: Determine whether the status information meets the warning conditions; If the aforementioned warning conditions are met, warning measures will be taken.

3. The battery status monitoring method according to claim 1, characterized in that, The step of obtaining the first parameter of the target battery based on the first index value and the first detection rule specifically includes: Based on the first indicator value and the first detection rule, the target fault type of the target battery and the target warning level corresponding to the target fault type are determined; The first parameter is obtained based on the target fault type and the target warning level.

4. The battery status monitoring method according to claim 1, characterized in that, The battery consistency detection rules include: consistency difference judgment conditions and fault module determination rules; The step of obtaining the consistency difference battery module based on the first SOC difference, the second SOC difference, and the battery consistency detection rule specifically includes: Based on the first SOC difference values ​​within the range from the first time point to the second time point, the trend of the first SOC difference value changing with time is obtained; Determine whether the trend of change satisfies the consistency difference judgment condition; If the consistency difference judgment condition is met, then the battery module with the consistency difference is determined according to the second SOC difference value within the range from the first time to the second time and the fault module determination rule.

5. The battery status monitoring method according to claim 1, characterized in that, The step of obtaining the thermal runaway index value of the target battery based on the temperature rise rate, the voltage drop rate, the thermal-related fault type warning frequency, and the thermal runaway index calculation rules specifically includes: The thermal runaway index value is obtained based on the temperature rise rate, the voltage drop rate, the warning frequency of the thermal-related fault type, and the preset weights corresponding to the thermal runaway index calculation rules. The preset weights are obtained based on the information entropy of historical data of the temperature rise rate, the voltage drop rate, and the warning frequency of the heat-related fault type.

6. The battery status monitoring method according to claim 4, characterized in that, The target battery is used in new energy vehicles; The method further includes: The thermal runaway index value of the target battery and the operating condition data of the new energy vehicle are input into the thermal runaway index value prediction model to obtain the predicted value of the thermal runaway index of the target battery at the target future time. Based on the predicted values ​​of the thermal runaway indicators, early warning measures shall be taken; The thermal runaway index prediction model is trained based on historical thermal runaway index values ​​and historical operating condition data.

7. A battery status monitoring device, characterized in that, include: The data acquisition module is used to acquire the operating data of the target battery; wherein, the operating data includes: time period operating data and current time period operating data; the time period operating data includes time period operating data within the range from a first time period to a second time period; the first time period is earlier than the second time period; the second time period is earlier than or equal to the current time period; The data processing module is used to obtain a first indicator value corresponding to a first monitoring indicator based on the running data at the time, and to obtain a second indicator value corresponding to a second monitoring indicator based on the running data during the time period. The parameter acquisition module is used to obtain a first parameter of the target battery based on the first indicator value and the first detection rule, and to obtain a second parameter based on the second indicator value, the first parameter time period sequence, and the second detection rule; wherein, the first detection rule includes a mapping relationship between the first parameter and the threshold range of the first indicator value; the first parameter time period sequence includes a sequence of the first parameters corresponding to each time point from the first time point to the second time point; A status monitoring module is used to determine the status information of the target battery based on the first parameter and / or the second parameter; The process of obtaining the second parameter based on the second indicator value, the first parameter time period sequence, and the second detection rule specifically includes: Based on the second index value, the first state of charge (SOC) difference and the second SOC difference, the temperature rise rate and the voltage drop rate are obtained; wherein, the target battery includes at least one battery module; the first SOC difference is the absolute value of the difference between the average SOC value and the minimum SOC value of each battery module; the second SOC difference is the absolute value of the difference between the SOC correction value of each battery module and the average SOC value; Based on the time period sequence of the first parameter, the warning frequency of heat-related fault types is obtained; The second parameter is obtained based on the first SOC difference, the second SOC difference, the temperature rise rate, the voltage drop rate, the thermal-related fault type warning frequency, and the second detection rule; The second detection rule includes: battery consistency detection rule and thermal runaway index calculation rule; the second parameter includes: battery modules with poor consistency and thermal runaway index value; The second parameter is obtained based on the first SOC difference, the second SOC difference, the temperature rise rate, the voltage drop rate, the thermally related fault type warning frequency, and the second detection rule, specifically including: The battery module with poor consistency is obtained based on the first SOC difference, the second SOC difference, and the battery consistency detection rule; The thermal runaway index value of the target battery is obtained based on the temperature rise rate, the voltage drop rate, the warning frequency of the thermal-related fault type, and the thermal runaway index calculation rules.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-6.

Images